STRLCPY/Maryam

Adding the --output and --api functionality. Tested by using = topicmodeling -i mixed.json -t json -m all-distilroberta-v1 --output report json testreport iris/topicmodeling topicmodeling -i mixed.json -t json -m all-distilroberta-v1 --api
Hatma Suryotrisongko committed 2 years ago

f46565d6

1 parent bd4089ee

Revision indexing in progress... (symbol navigation in revisions will be accurate after indexed)

■ ■ ■ ■ ■ ■

maryam/core/util/iris/plotly.py maryam/core/util/iris/plotlyutil.py

		skipped 11 lines
12	12		along with this program. If not, see <http://www.gnu.org/licenses/>.
13	13		"""
14	14
15		-	import plotly
	15	+	import plotlyutil
16	16
17	17		class main:
18	18
		skipped 20 lines

■ ■ ■ ■ ■ ■

maryam/core/util/iris/topic.py

		skipped 156 lines
157	157
158	158		topics, _ = topic_model.fit_transform(self.corpus)
159	159		print(topic_model.get_topic_info()[:6])
	160	+	output = topic_model.get_topic_info()
160	161
161	162		corpus_labeled = pd.DataFrame({'ClusterLabel': topics, 'Sentence': self.corpus})
162	163		if verbose == True:
		skipped 7 lines
170	171		print("Cluster #" + str(i) + " = ")
171	172		print(topic_model.get_topic(i))
172	173		i += 1
	174	+
	175	+	return output
173	176
174	177

■ ■ ■ ■ ■ ■ ■

maryam/modules/iris/topicmodeling.py

		skipped 14 lines
15	15		'author': 'Hatma Suryotrisongko',
16	16		'version': '0.1.0',
17	17		'description': 'Topic Modeling Algorithms.',
	18	+	'required': ('dask', 'scikit-learn', 'umap', 'bertopic', 'gensim'),
18	19		'options': (
19	20		('inputfile', None, True, 'Input file that contains the data', '-i', 'store', str),
20	21		('filetype', None, True, 'File type: csv/json', '-t', 'store', str),
		skipped 9 lines
30	31
31	32		run = self.topic(self.options['inputfile'], self.options['filetype'], self.options['showcharts'], self.options['verbose'])
32	33		run.run_sklearn_cluster_kmeans(self.options['pretrained_model'], self.options['showcharts'], self.options['verbose'])
33		-	run.run_topic_modeling_bertopic(self.options['pretrained_model'], self.options['verbose'])
	34	+
	35	+	results = run.run_topic_modeling_bertopic(self.options['pretrained_model'], self.options['verbose'])
	36	+	print("\n\nResults = \n")
	37	+	print( results )
	38	+
	39	+	output = {'results': results.to_json(orient="records") }
	40	+	print("\n\nOutput = \n")
	41	+	print( output )
	42	+
	43	+	inputfile = self.options['inputfile']
	44	+	self.save_gather(output, 'iris/topicmodeling', inputfile, output=self.options['output'])
	45	+
	46	+	return output
34	47
35	48
36	49		def module_run(self):
		skipped 1 lines